Skip to content

@xiaomi-research Xiaomi Research

Change the repository type filter

All

    Repositories list

    42 repositories

    • ufo

      Public
      Python
      •
      Other
      •1•1•0•0•Updated May 12, 2026May 12, 2026

    • traqpoint

      Public
      0•0•0•0•Updated May 12, 2026May 12, 2026

    • mecat

      Public
      Python
      •
      Apache License 2.0
      •7•41•1•0•Updated May 12, 2026May 12, 2026

    • onevl

      Public
      Python
      •0•19•0•0•Updated May 1, 2026May 1, 2026

    • tts-prism

      Public
      Python
      •
      Apache License 2.0
      •4•45•4•0•Updated Apr 27, 2026Apr 27, 2026

    • dasheng-lm

      Public
      Efficient audio understanding with general audio captions
      Python
      •
      Apache License 2.0
      •40•422•7•0•Updated Apr 24, 2026Apr 24, 2026

    • controlfoley

      Public
      ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
      text-to-audioaudio-generationfoley-sound-synthesis
      text-to-audioaudio-generationfoley-sound-synthesisfoley-arttext-video-to-audiotext-controlled-video-to-audioaudio-controlled-video-to-audio
      Python
      •
      Apache License 2.0
      •2•80•1•0•Updated Apr 22, 2026Apr 22, 2026

    • svor

      Public
      SVOR - Stable Video Object Removal
      Python
      •
      Apache License 2.0
      •6•85•0•1•Updated Apr 21, 2026Apr 21, 2026

    • unidrivevla

      Public
      UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
      Python
      •
      Apache License 2.0
      •12•167•6•1•Updated Apr 14, 2026Apr 14, 2026

    • mobilebench-ol

      Public
      Python
      •
      Apache License 2.0
      •0•9•0•0•Updated Apr 13, 2026Apr 13, 2026

    • iot_spec_llm

      Public
      Python
      •0•1•0•0•Updated Apr 13, 2026Apr 13, 2026

    • worldsplat

      Public
      [ICLR 2026] WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving
      Python
      •
      Apache License 2.0
      •3•40•3•0•Updated Mar 31, 2026Mar 31, 2026

    • colar

      Public
      [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
      Python
      •
      Apache License 2.0
      •7•94•2•0•Updated Mar 27, 2026Mar 27, 2026

    • acavcaps

      Public
      2•26•0•0•Updated Mar 27, 2026Mar 27, 2026

    • xares-llm

      Public
      XARES-LLM
      Python
      •
      Apache License 2.0
      •5•55•0•1•Updated Mar 26, 2026Mar 26, 2026

    • dasheng-glap

      Public
      Official Implementation of GLAP - General Language Audio Pretraining
      multilingualaudio-text-modelingaudio-text-retrieval
      multilingualaudio-text-modelingaudio-text-retrieval
      Python
      •
      Apache License 2.0
      •3•72•0•0•Updated Mar 25, 2026Mar 25, 2026

    • drivelaw

      Public
      [CVPR2026] DriveLaW: Unifying Planning and Video Generation in a Latent Driving World
      Python
      •
      Apache License 2.0
      •5•53•0•0•Updated Mar 25, 2026Mar 25, 2026

    • proactive-mobile

      Public
      ProactiveMobile
      0•2•2•0•Updated Mar 13, 2026Mar 13, 2026

    • recogdrive

      Public
      [ICLR 2026] ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
      reinforcement-learningautonomous-drivingdiffusion-policy
      reinforcement-learningautonomous-drivingdiffusion-policyvision-language-actionvision-language-modelsnavsimend-to-end-a
      Python
      •
      Apache License 2.0
      •65•526•9•0•Updated Mar 13, 2026Mar 13, 2026

    • dasheng-tokenizer

      Public
      State-of-the-art continious audio tokenization
      Apache License 2.0
      •0•38•0•0•Updated Mar 9, 2026Mar 9, 2026

    • guievalkit

      Public
      GUIEvalKit: Open-source Evaluation Toolkit for GUI Agents
      Python
      •
      Apache License 2.0
      •6•20•7•0•Updated Feb 26, 2026Feb 26, 2026

    • shuffle-r1

      Public
      Official code repository of Shuffle-R1
      Python
      •
      Apache License 2.0
      •3•101•0•0•Updated Feb 23, 2026Feb 23, 2026

    • gemmax

      Public
      Gemma-based Multilingual Machine Translation Models
      Shell
      •
      Apache License 2.0
      •5•47•0•0•Updated Feb 13, 2026Feb 13, 2026

    • dggt

      Public
      DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
      Python
      •
      Other
      •54•504•34•3•Updated Jan 15, 2026Jan 15, 2026

    • timeviper

      Public
      [CVPR'26] TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
      Python
      •0•26•1•0•Updated Jan 4, 2026Jan 4, 2026

    • hyperclick

      Public
      0•0•0•0•Updated Dec 22, 2025Dec 22, 2025

    • time-r1

      Public
      [NeurIPS'25] Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
      Python
      •
      Apache License 2.0
      •5•93•16•0•Updated Dec 14, 2025Dec 14, 2025

    • xiaomi-iot-suggest-llm

      Public
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Dec 2, 2025Dec 2, 2025

    • btl-ui

      Public
      [NeurIPS 2025] Implementation of the paper "BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent"
      Python
      •
      Apache License 2.0
      •1•18•1•0•Updated Nov 27, 2025Nov 27, 2025

    • backtrackagent

      Public
      Python
      •0•3•2•0•Updated Nov 18, 2025Nov 18, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.